eric/seriatim
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 4 Wiki Activity

Implemented a module to detect filler segments, and skip them for purposes of same-speaker segment coalescing

Browse Source
This commit is contained in:
Eric Rakestraw
2026-04-27 19:58:55 -05:00
parent bbfb8aba44
commit fb0519c561
9 changed files with 319 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
internal/coalesce/coalesce_test.go
View File

@@ -151,6 +151,20 @@ func TestApplyDropsBackchannelCategoryFromMergedSameSpeakerRun(t *testing.T) {
}
}
func TestApplyDropsFillerCategoryFromMergedSameSpeakerRun(t *testing.T) {
first := segment("a.json", 0, "Alice", 1, 2, "um")
first.Categories = []string{"filler"}
second := segment("a.json", 1, "Alice", 2.5, 3, "more")
got, _ := Apply(model.MergedTranscript{Segments: []model.Segment{first, second}}, 3)
if len(got.Segments) != 1 {
t.Fatalf("segment count = %d, want 1", len(got.Segments))
}
if got.Segments[0].Categories != nil {
t.Fatalf("categories = %v, want nil", got.Segments[0].Categories)
}
}
func TestApplySkipsDifferentSpeakerBackchannelAsMergeBlocker(t *testing.T) {
first := segment("a.json", 0, "Alice", 1, 2, "first")
backchannel := segment("b.json", 0, "Bob", 2.2, 2.5, "yeah")
@@ -172,6 +186,27 @@ func TestApplySkipsDifferentSpeakerBackchannelAsMergeBlocker(t *testing.T) {
}
}
func TestApplySkipsDifferentSpeakerFillerAsMergeBlocker(t *testing.T) {
first := segment("a.json", 0, "Alice", 1, 2, "first")
filler := segment("b.json", 0, "Bob", 2.2, 2.5, "um")
filler.Categories = []string{"filler"}
second := segment("a.json", 1, "Alice", 3, 4, "second")
got, summary := Apply(model.MergedTranscript{Segments: []model.Segment{first, filler, second}}, 3)
if summary.OriginalSegmentsMerged != 2 || summary.CoalescedSegments != 1 {
t.Fatalf("summary = %#v", summary)
}
if len(got.Segments) != 2 {
t.Fatalf("segment count = %d, want 2", len(got.Segments))
}
if got.Segments[0].Text != "first second" {
t.Fatalf("first output text = %q, want first second", got.Segments[0].Text)
}
if got.Segments[1].Text != "um" || !reflect.DeepEqual(got.Segments[1].Categories, []string{"filler"}) {
t.Fatalf("second output segment = %#v", got.Segments[1])
}
}
func TestApplyDifferentSpeakerNonBackchannelStillBlocksMerge(t *testing.T) {
first := segment("a.json", 0, "Alice", 1, 2, "first")
bob := segment("b.json", 0, "Bob", 2.2, 2.5, "interruption")